Skip to main content

Use ChatGPT to accelerator your research.

Project description

ChatResearch

pypi python version license precommit black Ruff

ChatResearch is a tool that uses OpenAI's GPT-3 to accelerate your research. It provides several features such as generating summary papers, fetching and summarizing papers from arxiv and bioarxiv, generating responses for review comments, and more.

Why ChatResearch?

Numerous projects and research endeavors have been undertaken in the realm of ChatGPT, yet none have met my specific requirements. As a result, I have resolved to create my own project, tailored to my personal preferences. I shall persist in refining and enhancing this project. Please do not hesitate to leave a star, and I am grateful for your support and ratings. I welcome any suggestions, proposals, and pull requests.

TODO

  • Multi thread and Asynchronous support
  • Format PDF output
  • Tune prompt to support latex
  • Support output latex
  • Fine-tune prompt
  • Generate Image
  • Add RSS support for multiple journal
  • Add GIF for document
  • Revise help message
  • Use config to set key

Features

  • Chat Config: Generate chatre.toml in current working directory or set environment variable OPENAI_API_KEY.
  • Chat Reviewer: Generate summary paper with specified research fields and language.
  • Chat Arxiv: Fetch and summary paper from arxiv with specified query and language.
  • Chat Response: Generate response for review comment with specified language.
  • Chat Paper: Fetch or summary paper from local or arxiv with specified query, research fields, and language.
  • Chat Biorxiv: Fetch and summary paper from bioarxiv with specified category, filter keys, and language.
  • Markdown and PDF report

Installation

$pip install chat-research

Usage

Chat Config

❯ chatre config

It will generate chatre.toml in current working directory. Otherwise, setting environment variable OPENAI_API_KEY is another way to config API KEY.

[OpenAI]
OPENAI_API_KEYS = [ "sk-key1", "sk-key2",]

[Gitee]
api = "your_gitee_api"
owner = "your_gitee_name"
repo = "your_repo_name"
path = "files_name_in_your_repo"

Chat Reviewer

> chatre reviewer -h
usage: chatre reviewer [-h] --paper-path  [--file-format] [--review-format] [--research-fields] [--language]

optional arguments:
  -h, --help          show this help message and exit
  --paper-path        path of papers
  --file-format       output file format (default: txt)
  --review-format     review format
  --research-fields   the research fields of paper (default: computer science, artificial intelligence and reinforcement learning)
  --language          output language, en or zh (default: en)

Chat Arxiv

Chat Response

Chat Paper

Chat Biorxiv

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributors

  • Yangyang Li

Alt

Acknowledgement

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

chat_research-0.1.7.tar.gz (42.4 kB view details)

Uploaded Source

Built Distribution

chat_research-0.1.7-py3-none-any.whl (67.3 kB view details)

Uploaded Python 3

File details

Details for the file chat_research-0.1.7.tar.gz.

File metadata

  • Download URL: chat_research-0.1.7.tar.gz
  • Upload date:
  • Size: 42.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for chat_research-0.1.7.tar.gz
Algorithm Hash digest
SHA256 1f2deddff66ec9d7078763a13c4a098896677245e6a5267284f4b5951b675d90
MD5 58abb51e4260bef35ebd0b753e4a1919
BLAKE2b-256 2f35f675e3dd414de4926ceb67e0daeddcda9a63848ee3ec0d87ca749a897df3

See more details on using hashes here.

File details

Details for the file chat_research-0.1.7-py3-none-any.whl.

File metadata

File hashes

Hashes for chat_research-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 8271fd5eec9ef05668a5058305cb24c3d00d7dae413605639fc59c7e92823db5
MD5 05625f1caf24d97d04e49368ccc7a11f
BLAKE2b-256 b2778ebb1331d1c54e4f3b97d82fd97524d7a05848f73fc256b4975d8f9b6e31

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page